add a dbt_pii project to start on the macro

dbt_pii/.gitignore

@@ -0,0 +1 @@
+dbs/*.db

dbt_pii/README.md

@@ -0,0 +1,14 @@
+# dbt pii
+
+A dbt macro which detects pii.
+
+## Getting Started
+
+To get started, run the following:
+
+```
+poetry install
+poetry run dbt seed --profiles-dir .
+poetry run dbt run --profiles-dir .
+sqlite3 dbs/main.db 'select * from main.pii_info;'
+```

dbt_pii/dbt_project.yml

@@ -0,0 +1,33 @@
+name: 'dbt_pii'
+version: '1.0.0'
+config-version: 2
+
+# This setting configures which "profile" dbt uses for this project.
+profile: 'dbt_sqlite'
+
+# These configurations specify where dbt should look for different types of files.
+# The `source-paths` config, for example, states that models in this project can be
+# found in the "models/" directory. You probably won't need to change these!
+model-paths: ["models"]
+analysis-paths: ["analysis"]
+test-paths: ["tests"]
+seed-paths: ["seeds"]
+macro-paths: ["macros"]
+snapshot-paths: ["snapshots"]
+docs-paths: ["docs"]
+
+target-path: "target"  # directory which will store compiled SQL files
+clean-targets:         # directories to be removed by `dbt clean`
+    - "target"
+    - "dbt_modules"
+
+
+# Configuring models
+# Full documentation: https://docs.getdbt.com/docs/configuring-models
+
+# In this example config, we tell dbt to build all models in the example/ directory
+# as tables. These settings can be overridden in the individual model files
+# using the `{{ config(...) }}` macro.
+models:
+  pii:
+      +materialized: table

dbt_pii/models/models.yml

@@ -0,0 +1,11 @@
+version: 2
+
+models:
+  - name: pii_info
+    description: Fact table for orders including customer and cohort dimensions.
+    columns:
+      - name: id
+      - name: name
+      - name: city
+      - name: comments
+      - name: pii

dbt_pii/models/pii_info.sql

@@ -0,0 +1,7 @@
+select
+  id,
+  name,
+  city,
+  comments,
+  "pii" as pii
+from {{ ref('info') }}

dbt_pii/models/sources.yml

@@ -0,0 +1,14 @@
+version: 2
+
+sources:
+  - name: info
+    schema: info
+    loader: SQLite CLI
+    tables:
+      - name: info
+        description: Fact table for orders including customer and cohort dimensions.
+        columns:
+          - name: id
+          - name: name
+          - name: city
+          - name: comments

dbt_pii/profiles.yml

@@ -0,0 +1,17 @@
+# For more information on how to configure this file, please see:
+# https://docs.getdbt.com/docs/profile
+config:
+  send_anonymous_usage_stats: false
+  use_colors: true
+
+dbt_sqlite:
+  target: dev
+  outputs:
+    dev:
+      type: sqlite
+      threads: 1
+      database: database
+      schema: main
+      schemas_and_paths:
+        main: "{{ env_var('PWD') }}/dbs/main.db"
+      schema_directory: "{{ env_var('PWD') }}/dbs"

dbt_pii/pyproject.toml

@@ -0,0 +1,16 @@
+[tool.poetry]
+name = "dbt-pii"
+version = "0.1.0"
+description = ""
+authors = ["Your Name <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.12"
+dbt = "^1.0.0.38.13"
+dbt-sqlite = "^1.5.0"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

dbt_pii/seeds/info.csv

@@ -0,0 +1,4 @@
+id,name,city,comments
+1,Sowmya,New York,called him yesterday to confirm he requested to call back in 2 days
+2,Jill,Los Angeles,accepted the offer license number AC432223
+3,Jack,Chicago,need to call him at phone number 212-555-5555